Intelligent Image-based-Visual Servoing for Quadrotor Air Vehicle

Abstract

Since quadrotors are becoming more popular, several techniques appeared to control robustly the Unmanned Aerial Vehicle. This article proposes an intelligent image-based visual servoing (IBVS) control method for an unmanned aerial vehicle (UAV). This work consists of computing the proportional controller gain by smoothing the error between the desired and actual feature vectors values, as opposed to the classical visual servoing (VS) scheme. The weak handling of this gain, affect the maintaining of tracked features in the area of view. Unlike the classical VS scheme that requires a known value of gain, selected in a heuristic way, which lead the controller to fall in the velocity convergence problem. We adjust an adaptive gain value by the use of a fuzzy logic controller. The proposed controller exploits the error between feature vectors and its derivative as inputs. Furthermore, we design an intelligent based-fuzzy logic method for gain tuning of PD controllers applied for handling the heading and position of the quadrotor. The proposed controllers are applied to the inner and outer loop, offer several advantages in dealing the uncertainty occurred within trajectory tracking control. Various simulations are developed in MATLAB, shows the outperformance of the proposed method against the classical one.